They would need 250 million GPT Plus $20 subscribers to recoup a $5 billion expense. They're far from that even when we count the free users (which are likely 99% of the user base?)

The math just doesn't work. They're hemorrhaging money as far as I can tell (not counting the Azure computing deal).

We can only guess, but my guess is that inference is still a good chunk of their costs. That's why they're trying to get the mini/turbo models into a usable state.

Even then, training is still an expense. And it's not like you can train and forget. Even if your model is already trained you still need to incorporate new knowledge over time.